Agent frameworks & infrastructure

LLM gateways & API proxies

4,018 agents · most starred first

LLM gateways & API proxies, page 11 of 41

langchain-codex-oauth★ 14

[LEGACY] Use the Codex models included with a ChatGPT Plus/Pro subscription inside LangChain/LangGraph.

go-llm★ 14

Agentic Assistant Application, CLI and API

ai-cli-bridge★ 14

Use your Claude Max / ChatGPT Pro subscription as an API. Self-hosted Express + Bun HTTP bridge that wraps the Claude Code CLI and OpenAI Codex CLI into an authenticated REST API with SSE streaming, hashed API keys, per-user rate limits, token & cost tracking, request logs, and an admin dashboard.

thalamus★ 14

Use your Cursor subscription to power Claude Code — smart proxy with lazy tool loading, auto-continuation & model fallback

pi-xai★ 14

Pi extension for SpaceXAI Grok/X.com Subscriptions

switch-plus-plus★ 14

Agent Switch: Claude Code, Claude Desktop, Codex CLI, Codex Desktop, Hermes, OpenCode, OpenClaw and AI agent config switcher, model router, and local OpenAI/Anthropic gateway

hf-llm-api★ 14

docker region:us

Open_gpt4O_fast★ 14

gradio region:us

pxpipe-windows★ 14

Windows fork of pxpipe: transparent Fable 5 compression for Claude Desktop on Windows 11.

xuanji★ 14

璇玑 Xuanji —— Go 单二进制 AI 网关,OpenAI / Anthropic 双协议汇聚。one-api / new-api / LiteLLM 轻量替代品,自动分流、负载、重试,成本优先路由,高可用不中断。

mirasim-relay-bridge★ 14

把 Mirasim 内置的 Anthropic 反代成API直接调用

veroroute-edge★ 14

Zero-weight AI gateway for Cloudflare Workers • Gateway de IA zero-peso para Cloudflare Workers. Multi-provider routing with auto-fallback, key pool, OpenAI+Anthropic endpoints, context compression & RAG search. One-click deploy.

LLM-Reasoning-Router★ 14

docker region:us

zcode-bridge★ 14

OpenAI- and Anthropic-compatible local gateway for ZCode plan quota. Single Go binary, stdlib only.

langchain-provider★ 13

Basic completions provider using Langchain and OpenAI like APIs for Spyder 6+

RyuzakiLib★ 13

RyuzakiLib is a downloader tool, ChatGPT Free, FluxAI Free, image generator [PYTHON-BACKEND] all supported

rsnchat-js★ 13

The package for AI chats and AI images.

AgentGate★ 13

One app to switch Codex / Claude Code / Gemini CLI between DeepSeek, OpenAI, Claude, Kimi & 20+ providers. Protocol conversion, smart failover, vision routing. No config files — just click.

litellm-server-boilerplate★ 13

A lightweight LiteLLM server boilerplate pre-configured with uv and Docker for hosting your own OpenAI- and Anthropic-compatible endpoints. Includes LibreChat as an optional web UI.

anthropic-react-native★ 13

Anthropic API React Native Client without polyfills

Antigravity-Claude-Code-Proxy★ 13

Local multi-provider gateway for using Claude Code with Gemini, GPT, Grok, and other models, with account rotation and monitoring.

claude-cruise★ 13

Never hit a rate limit again.

rosetta-llm★ 13

Multi-format LLM proxy — translates OpenAI Chat, OpenAI Responses & Anthropic Messages. Works as a Claude Code LLM gateway with full model picker support.

sturnus★ 13

Latency-based load balancing across OpenAI, Azure OpenAI, Vertex AI and Anthropic. An OpenAI-compatible sidecar in a single static binary.

claude2api★ 13

docker region:us

wallasapi★ 13

The unified, OpenAI-compatible AI router. 12+ providers, 100+ models, automatic fallback. Built solo from a rented room in Peru. Star + donate to keep it alive.

ai-switch★ 13

本地 AI Key 中枢:一把 Key 改完,OpenClaw / OpenCode / Codex / Claude Code 立刻能用;坏 Key 自动踢出,不把工具搞挂。

Mithril★ 13

Multi-model orchestration engine. Combine any LLM providers (Gemini, OpenAI, Anthropic, Groq, local GGUF) into a single Ollama-compatible API. 24 tools, multi-agent, Docker ready.

router★ 13

Local-first hybrid LLM router for policy-aware local/cloud inference

Opencode2api★ 13

🚀 High-performance OpenAI & Anthropic compatible API gateway and React 19 control plane for OpenCode Zen free tier with 100% resilience.

unifyroute★ 12

Stop being locked into one LLM provider. UnifyRoute is a self-hosted gateway that routes, fails over, and manages quotas across OpenAI, Anthropic, and more with a drop-in OpenAI-compatible API.

anthrogo★ 12

Anthropic api wrapper for Go

nadiru-engine★ 12

Sovereign AI orchestration engine with a learning Conductor. Routes between 400+ models across 15+ providers. Streams responses, detects refusals, learns from your patterns.

aura-llm-gateway★ 12

High-performance Rust LLM gateway implementing the Open Responses API. Unified access to OpenAI, Anthropic, Google, Mistral, Ollama, HuggingFace, and AWS Bedrock with cost tracking, prompt compression, smart routing, and encrypted credentials.

ai-sub-auth★ 12

Reuse your AI subscriptions. One module, every provider. OAuth PKCE for ChatGPT Plus/Pro, API keys for Claude/Gemini/DeepSeek, device code for Copilot. ~500 LOC, only depends on httpx.

router★ 12

Route inference calls to different providers based on a fallback condition, or a routing rule you define.

nullsink★ 12

Privacy-first, account-less metered proxy for frontier models. No account, no IP, no request logs.

claude-cursor-proxy★ 12

Local proxy so Claude Code and grok-build (Grok CLI) can use Cursor models (Fable), plus Codex, Kimi, and Grok

atoma★ 12

Cost-aware three-tier LLM agent orchestration: the cheapest model that can answer, per-call cost accounting, earned trust

semanticrouter-go★ 11

Fast & less costly AI decision making and intelligent processing of multi-modal data.

DQIII8★ 11

Works for you. Go outside and live. — AI orchestrator that auto-routes tasks to the cheapest model that solves them. 70% run free on local models. Self-auditing, self-improving, zero prompting skill needed. Built with vibe coding by a finance student. Your models, your data.

anthropic-bridge★ 11

Proxy server that translates Anthropic Messages API requests to OpenRouter, enabling use of Gemini, OpenAI, Grok, DeepSeek, and other LLMs through an Anthropic-compatible interface.

claudex★ 11

Bridge Claude Code to ChatGPT Codex via a local Anthropic-compatible proxy.

AbstractCore★ 11

Build your app on AI capabilities, not on providers. AbstractCore is one abstraction layer over open-source and cloud models: it understands and generates text, images, voice, music, video and 3D, so you design once and never deal with how each capability is wired.

sharequota.com★ 11

Every AI plan you own, behind one key. A free, MIT-licensed local AI gateway that pools Claude, ChatGPT, Gemini, DeepSeek and OpenRouter into a single endpoint — one key for Claude Code, Codex and Gemini CLI. No account, no server in the middle, nothing leaves your machine.

dooo★ 10

1 universal function to do anything with LLMs. Painlessly swap between 100+ LLMs.

rabb1tClaw★ 10

Self-hosted Rust LLM gateway for the Rabbit R1. WebSocket streaming, sandboxed Python agents, OpenAI / Anthropic / OpenAI-compatible providers.

codex-provider★ 10

Agent Zero plugin: Use your ChatGPT subscription to power Agent Zero with OpenAI Codex models via OAuth

OAI2LMApi★ 10

OpenAI to Language Model API Bridge - Use OpenAI-Compatible API in Copilot - [VScode Extension]

go-openrouter★ 10

OpenRouter Go SDK

ChatGTP-NODE-JS-API-CALL★ 10

A simple Nodejs function to call the ChatGTP endpoint

OpenAI-to-Claude-API-Converter-Proxy★ 10

A local proxy server that converts and forwards OpenAI API format endpoints to Anthropic Claude API format

go-deepseek★ 10

A Go client for DeepSeek-compatible APIs, supporting chat, streaming, function calling, FIM, embeddings, balance queries, and Ollama/OpenAI/Qwen integration.

Simple-ChatGPT-Backend★ 10

Basic Express.js app built with TypeScript. It provides an interface between client applications and OpenAI's API

clauver★ 10

CLI tool to manage and switch between Claude Code API providers including Anthropic, MiniMax, Z.AI, Kimi, KAT-Coder, and custom providers.

RoBC★ 10

RoBC is an online learning LLM router designed for dynamic production environments. Using Thompson Sampling and semantic clustering, it continuously adapts to changing model quality—no retraining required.

cli-switch★ 10

AI Agent Capability Router for Claude Code, Codex CLI, self-hosted LLM relays, OpenRouter-compatible gateways, and automation workflows.|作者周维天(小天说FDE,杭州 FDE)

openclaw-model-bridge★ 10

OpenClaw Runtime Control Plane for Tool-Calling Agents — 13-provider routing with capability-aware fallback, tool governance, ontology-driven governance (91 invariants), and a sabotage-validated fail-plausible observer. arXiv:2606.14589

talon★ 10

Open-source AI governance gateway for EU teams: enforce PII, cost, model, data residency, and tool policies for LLMs and AI agents with signed evidence.

Model_Router★ 10

Dynamically route tasks to the best AI model and configuration using an LLM-powered intelligent selection system.

chat-rs★ 10

A multi-provider LLM framework for Rust.

llmapi-cli★ 10

Command-line client and python development library for accessing LLM's OpenAPI :computer:

taalas-chatjimmy-wrapper★ 10

Unofficial OpenAI-compatible wrapper in front of chatjimmy.ai (by Taalas) for the llama-3.1:8B model, which aims to deliver ~17,000 tokens per second, per user.

heimsense★ 10

Unlock Your Claude Code for Any LLM

deepseek-responses-proxy★ 10

Local Responses API shim for Codex custom providers backed by DeepSeek/OpenAI Chat Completions

LLMate★ 10

LiteLLM for the JVM. One Spring Boot gateway for OpenAI, Anthropic, Gemini, Ollama & 12 more providers. Aliases, fallbacks, streaming, RAG - zero SDK juggling.

crabllm★ 10

Blazing fast LLM gateway, guardrails, load balancing and logging.

octolib★ 10

One Rust API for 30+ AI providers — chat, tool calls, structured output, embeddings, reranking and media generation behind a single provider:model string, with built-in cost tracking

ferryllm★ 10

Universal LLM protocol middleware for OpenAI, Anthropic, Claude Code, and OpenAI-compatible backends.

syfthub★ 10
ostk-cache★ 10

Context-aware caching proxy for Anthropic and OpenAI — maximizes prompt-cache hit rates by anchoring long-lived context into stable boundaries. Drop-in for Claude Code, Codex, Cursor, and custom harnesses.

claude-relay★ 10

Drop-in OpenAI and Anthropic API server that routes through Claude Code

relay-api-hub★ 10

你买的 AI API 掺水了吗?一键检测 Claude/GPT/Gemini 中转站是否用廉价模型冒充

claude-oauth-proxy★ 10

Local OAuth proxy for Anthropic Teams/Enterprise — auto-manages tokens, streams SSE with zero buffering

busytok★ 10

Task-level model routing through persistent subagents, with local-first GUI and CLI orchestration

fusion-engine★ 10

Self-hosted Fusion API and OpenRouter Fusion alternative for building reliable multi-model LLM ensembles — fan out one prompt to N models, then synthesize one answer with a judge model. OpenAI-compatible API, CLI, and eval harness.

relay★ 10

Universal AI API proxy — hot-switch between any LLM provider (GitHub Copilot, OpenAI, Anthropic, Z.AI, MiniMax, DeepSeek, Groq, Ollama, and more) from any AI coding agent (Claude Code, ForgeCode, OpenAI Codex CLI, OpenCode, Cline, Aider, Continue)

codex-gateway★ 10

🛜 codex-gateway: Forward your codex subscription to openai api

claude-tweaks★ 10

Reversible macOS patcher for Claude Desktop ASAR tweaks, including third-party inference routing, Computer Use experiments, and an optional desktop pet overlay.

PuterAI-Gateway★ 10

Free, unlimited access to GPT-5.5 Pro, Claude Opus 4.7, Gemini 3.1 Pro/Flash, and DeepSeek V4 — no API keys needed.

codex-openai-proxy★ 10

A local OpenAI-compatible proxy that reuses ~/.codex/auth.json to forward requests to the Codex backend API, with support for models, responses, and chat/completions.

codex-vercel-proxy★ 10

A Codex proxy with credential pooling and token refresh, deployable on Vercel.

claude-api-bridge★ 10

Turn your Claude Code subscription into a REST API. Access Claude Code from anywhere with a single command.

hermes-cli-orchestrator★ 10

Control plane plugin for Hermes Agent — pool many free/cheap model providers + local AI CLIs, switch brains from Telegram in one command (even while the model is down), delegate work cap-aware with auto-fallback. Run your agent at ~$0 without hitting quota walls.

openrouter-php★ 10

A modern, fully-typed PHP client for the OpenRouter API — chat, streaming, tools, structured outputs, memory & more.

freegate★ 10

Multi-upstream OpenAI-compatible AI proxy for free models, routed through Tor. HTMX dashboard.

relay★ 10

Self-hosted LLM gateway + model router. One static binary, OpenAI & Anthropic dialects in, any provider out, zero telemetry.

aviary★ 10

One chat-completion API across many LLM providers, for Raven. OpenAI, Anthropic, Gemini, Cohere, Groq, Mistral, and more.

free-claude-code-nvidia★ 10

Use Claude Code 100% free with 100+ NVIDIA NIM models via LiteLLM proxy. No Anthropic subscription needed. Works on Windows & macOS.

AngeMedia-gateway★ 10

OpenAI-compatible media generation gateway for AI Agents. Supports multi-provider image/video generation, model routing, prompt enhancement, and built-in Web Studio.

tokenpanel★ 10

Open-source AI reseller panel with customer API keys, prepaid balances, usage limits, model pricing, and profit analytics.

openhinge★ 10

Self-hosted AI gateway — unify Claude, OpenAI, Gemini & Ollama behind a single OpenAI-compatible API

yaoshu-token★ 10

爻枢 Token 智能网关、Token 智能聚合、大模型评测、排名等。关注“爻枢未来”公众号获得更多全自动编程详情。

Codex-Autorouter★ 10

Automatic GPT-5.6 model, effort, and subagent routing for Codex—optimized for precision, speed, and total token cost.

claude-dialects★ 10

Isolated Claude Code dialects for Codex, Kimi, Cursor, Copilot, Gemini & more — embedded CLIProxyAPI, no manual proxy setup. macOS only.

hydra★ 10

The AI control plane for software development. Discovers every model on your machine, routes by capability and cost, enforces PII policy, tracks spend.

unified-ai-system★ 10

Self-hosted model routing gateway and agent control plane for OpenAI, Anthropic, Gemini and A2A agents behind one OpenAI-compatible API, protocol-first. MCP server security, governed tools, prompt enhancement, virtual-key budgets, cache, observability, audit chain and agent governance. Zero-key loca

dsh-codex-oauth★ 10

Use your OpenAI subscription with DeepSeek Harness to access GPT models, image generation, and web search.

codex-account-switcher★ 10

Open-source Windows app to switch multiple OpenAI Codex accounts, view 5-hour and weekly limits, encrypt profiles with DPAPI, and control Codex or V2RayTun from Telegram.

litellm-operator★ 10

Kubernetes operator for deploying and managing LiteLLM AI Gateway. Declarative CRDs for models, teams, users, and virtual keys with bidirectional config sync, SSO/SCIM user provisioning, and OLM support. Built with Operator SDK.

More in Agent frameworks & infrastructure